CN103247008B - A kind of method for evaluating quality of electricity statistical index data - Google Patents
A kind of method for evaluating quality of electricity statistical index data Download PDFInfo
- Publication number
- CN103247008B CN103247008B CN201310163339.9A CN201310163339A CN103247008B CN 103247008 B CN103247008 B CN 103247008B CN 201310163339 A CN201310163339 A CN 201310163339A CN 103247008 B CN103247008 B CN 103247008B
- Authority
- CN
- China
- Prior art keywords
- data
- index data
- statistical index
- electricity statistical
- quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 202
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 claims abstract description 18
- 238000013441 quality evaluation Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 16
- 239000000654 additive Substances 0.000 claims description 11
- 230000000996 additive effect Effects 0.000 claims description 11
- 230000032683 aging Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 8
- 230000008034 disappearance Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000011160 research Methods 0.000 claims description 5
- 230000002950 deficient Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 11
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000012372 quality testing Methods 0.000 description 3
- 238000009472 formulation Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000001303 quality assessment method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of method for evaluating quality of electricity statistical index data, comprise the following steps: according to the needs of actual assessment object, obtain electricity statistical index data to be assessed; Select corresponding data quality accessment index; Formulate the data quality accessment rule corresponding with each quality evaluation index; Calculated mass evaluation index I
iweights W
iand set expectation value E
i; Statistical index data is carried out to the detection analysis of each quality evaluation index, and calculate and meet quality evaluation index I
idata number percent S
i; According to weights W
i, qualified number percent S
iwith the expectation value E of setting
i, calculate the comprehensive assessment value SA of statistical index data, overall expectation value SE and relative difference SR respectively, and according to the opinion rating of setting, statistical index data oeverall quality assessed; The underproof statistical index data evaluated is processed.The present invention can be applied in the quality evaluation of the electricity statistical index data of power industry.
Description
Technical field
The present invention relates to a kind of Data Quality Assessment Methodology, particularly about a kind of method for evaluating quality being applicable to the electricity statistical index data of power industry.
Background technology
In recent years, along with the fast development of electric utility, each department of Utilities Electric Co. all have accumulated data that are more and more, that become increasingly complex, simultaneously also increasing to the demand of electric power statistical information, requires more and more higher.The effect that statistical information plays in corporate decision, operation control and social responsibility are born is also more and more important.But, due to the artificial and unartificial disturbance of Utilities Electric Co.'s data acquisition system (DAS), the quality of data of each data source can be caused uneven, in addition some problem of database itself, cause, when data integration, shortage of data and mistake occur, thus cause data total quality not high, corporate decision's planning and development are had an impact, therefore quality evaluation is carried out to statistics and will to become in development of company process a necessary link.
Comparatively perfect electricity statistical index data system has been had in prior art, but seldom have and carry out for the data in statistical index data system the method for evaluating quality that rationality, standardization and authenticity detect analysis, data quality accessment is often just sporadically for index important in quality of data statistical indicator, as consistance, uniqueness, integrality etc. are carried out, not yet form systematized Data Quality Assessment Methodology.
Summary of the invention
For the problems referred to above, the object of this invention is to provide a kind of method for evaluating quality of electricity statistical index data, can rationally, specification, truly electricity statistical index data quality to be assessed.
For achieving the above object, the present invention takes following technical scheme: a kind of method for evaluating quality of electricity statistical index data, it comprises the following steps: 1) according to the needs of actual assessment object, arrange electricity statistical index data, obtains electricity statistical index data to be assessed; 2) according to described electricity statistical index data to be assessed, corresponding data quality accessment index I is selected
i(i=1 ... .n, n is the number of data quality accessment index); 3) according to electricity statistical index data to be assessed and selected data quality accessment index I
i, formulate the data quality accessment rule R that each data quality accessment index is corresponding
r(I
i); 4) each data quality accessment index I is calculated
iweights W
iand respective settings expectation value E
i; 5) according to step 3) the middle data quality accessment rule R formulated
r(I
i), detection is carried out to electricity statistical index data to be assessed and analyzes, and calculate and meet each data quality accessment index I
idata number percent S
i, S
ibetween 0 to 100; 6) according to step 4) weights W that calculates
i, qualified number percent S
iwith the expectation value E of setting
i, calculate the comprehensive assessment value SA of described electricity statistical index data to be assessed, overall expectation value SE and relative difference SR respectively, and according to the opinion rating of setting, described electricity statistical index data oeverall quality to be assessed assessed; 7) the defective electricity statistical index data evaluated is processed; 8) relative difference SR and overall expectation value SE is compared, obtain electricity statistical index data D to be assessed totally relative to the quality condition of overall expectation value SE, detailed process is: if SR symbol is just, overall expectation value SE is larger for its numeric ratio, then better than expection of the overall quality of data of described electricity statistical index data to be assessed is described; If SR symbol is negative, overall expectation value SE is larger for its numeric ratio, then the poorer of the quality of data ratio expection that described electricity statistical index data to be assessed is overall is described.
Described step 2) in data quality accessment index be correctness, integrality, uniqueness, consistance, accuracy, validity and ageing in some or certain is several.
Described step 3) in each data quality accessment rule R
r(I
i) according to the characteristic sum attribute of electricity statistical index data to be assessed and selected data quality accessment index I
idefinition formulate.
Described step 4) each quality evaluation index I of middle calculating
iweights W
iadopt analytical hierarchy process, the steps include: 1. according to data quality accessment index I
iimportance Scaling implication table, determine each data quality accessment index I by list mode
ibetween Scaling, and then obtain judgment matrix; 2. all importance degree values in the judgment matrix 1. obtained step carry out row normalized respectively, obtain row normalization matrix; 3. summation operation is carried out to each row of row normalization matrix, obtain row additive value; 4. carrying out summation operation to obtaining all row additive values, obtaining row and being added total value; 5. each data quality accessment index I is calculated
iweight, i.e. weight=row additive value/row is added total value.
Described step 6) in opinion rating be: if SA ∈ (95,100 ］ the overall data quality level of electricity statistical index data to be assessed is then evaluated for " excellent ", if SA ∈ (90,95 ］ the overall data quality level of electricity statistical index data to be assessed is then evaluated for " good ", if SA ∈ (85,90 ］ then evaluate the overall data quality level of electricity statistical index data to be assessed for " in ", if SA ∈ (0,85 ］ then evaluate the overall data quality level of electricity statistical index data to be assessed for " poor ".
Described step 7) in the underproof electricity statistical index data evaluated is processed, its concrete processing procedure comprises: revise the electricity statistical index data of exception; The electricity statistical index data of disappearance is filled up; The electricity statistical index data repeated is deleted; Expression format disunity, electricity statistical index data that numerical value is invalid are revised; The underproof electricity statistical index data of logarithm value precision is modified; The electricity statistical index data not strong to existing research availability is deleted.
The present invention is owing to taking above technical scheme, it has the following advantages: 1, the present invention is according to the electricity statistical index data to be assessed obtained, select corresponding data quality accessment index, correctness can be comprised, integrality, uniqueness, consistance, accuracy, validity and ageing, and according to electricity statistical index data to be assessed and selected data quality accessment index, formulate corresponding data quality accessment rule, carry out detection by the data quality accessment rule formulated to electricity statistical index data to analyze, calculate the comprehensive assessment value SA of electricity statistical index data, and assess according to the quality of opinion rating to electricity statistical index data of setting, therefore the present invention can carry out rationally to the statistical index data of power industry, specification and assessing truly.2, relative difference SR and overall expectation value SE compares by the present invention, obtain electricity statistical index data D to be assessed totally relative to the quality condition of overall expectation value SE, detailed process is: if SR symbol is just, overall expectation value SE is larger for its numeric ratio, then better than expection of the overall quality of data of described electricity statistical index data to be assessed is described; If SR symbol is negative, overall expectation value SE is larger for its numeric ratio, the poorer of the quality of data ratio expection that described electricity statistical index data to be assessed is overall is then described, therefore the present invention can provide and carry out forecast analysis to the total quality situation of electricity statistical index data to be assessed, the further degree of depth excavates the inherent law of electricity statistical index data, effective raising company is to the application degree of depth of electricity statistical index data and supervisory role, and help company makes scientific and reasonable decision-making.3, the present invention is owing to can evaluate from opinion rating and oeverall quality situation two aspects electric power statistics to be assessed, therefore power industry associated companies can be helped to understand the overall quality level of statistical index data, Timeliness coverage data quality problem, and the repair data quality problems that take appropriate measures, improve the quality of data.The present invention can be applied in the quality evaluation of the electricity statistical index data of power industry.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of method for evaluating quality of the present invention
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in detail.
As shown in Figure 1, the method for evaluating quality of electricity statistical index data of the present invention, comprises the following steps:
1) according to the needs of actual assessment object, electricity statistical index data is arranged, obtain electricity statistical index data D to be assessed;
Electricity statistical index data is many and complicated, relates to multiple scope of business, as: the aspects such as operation of power networks, device fabrication, human resources and assets are dynamic.Because the object assessed is not necessarily identical at every turn, therefore selected electricity statistical index data is also not necessarily identical.Electricity statistical index data can be the data in same electric power statistical report form, also can be the multiple statistical index data in different form.Therefore, to need according to actual assessment object, to many and the electricity statistical index data of complexity arranges, to obtain electricity statistical index data D to be assessed before assessment.
The present invention with certain year some electrical power statistical index data for embodiment illustrates, as shown in table 1, electricity statistical index data D to be assessed comprises line loss per unit, delivery, line loss electricity, average load factor, the highest generation load of Home Network and whole society user number six electricity statistical index data.
Table 1 certain year some electrical power statistical index data table
2) according to electricity statistical index data D to be assessed, corresponding data quality accessment index I is selected
i;
Because the quality of electricity statistical index data has different definition under different backgrounds, different users is different to the focus of electricity statistical index data, and therefore selected data quality accessment index is also different.At present, electricity statistical index data is just presenting the situation of explosive increase, and there is the problems such as data exception, shortage of data, Attribute Redundancy and form be lack of standardization, therefore, in conjunction with the practical significance of electricity statistical index data to be assessed, some or a few data quality accessment index I can be chosen from existing data quality accessment index
i(i=1,2...n, wherein n is the number of data quality accessment index) assesses electricity statistical index data to be assessed, and this is not restricted.Embodiments of the invention are chosen the quality of correctness, integrality, uniqueness, consistance, accuracy and validity six data quality accessment indexs to electricity statistical index data D to be assessed and are assessed.Correctness is used for assessing with input correctness the true accordance of electricity statistical index data D to be assessed; Integrality is used for whether electricity statistical index data D to be assessed is existed to disappearance record or lack field assessing; The record that uniqueness is used for whether existing electricity statistical index data D to be assessed repetition is assessed; Whether consistance is used for unanimously assessing the expression format of electricity statistical index data D to be assessed; Whether accuracy is used for accurately assessing the precision of electricity statistical index data D to be assessed; Whether validity is used for effectively assessing the form of electricity statistical index data D to be assessed and numerical value.
3) according to electricity statistical index data D to be assessed and selected data quality accessment index I
i, formulate data quality accessment rule R
r(I
i);
According to characteristic sum attribute and the selected data quality accessment index I of electricity statistical index data D to be assessed
idefinition formulation and data quality accessment index I
icorresponding data quality accessment rule R
r(I
i) (i=1,2...n, wherein n is the number of data quality accessment index).Generally, the data quality accessment rule of correctness refers to that electricity statistical index data is as good as constant value; The data quality accessment rule of integrality refers to that electricity statistical index data is without null value; The data quality accessment rule of uniqueness refers to that electricity statistical index data is unique, nothing repeats; Conforming data quality accessment rule refers to that the expression-form of electricity statistical index data is consistent; The data quality accessment rule of accuracy refers to that the precision of electricity statistical index data is unified; Validity data quality accessment rule refer to the attribute of electricity statistical index data and form effective.
The data quality accessment rule that the present invention is directed to above-described embodiment formulation is as shown in table 2:
Table 2 data quality accessment rule list
4) data quality accessment index I is calculated
iweights W
iand according to actual assessment object need set expectation value E
i;
The present invention adopts analytical hierarchy process to calculate the weights W of data quality accessment index
i, it comprises the following steps:
1. according to data quality accessment index I
iimportance Scaling implication table, determine each data quality accessment index I by list mode
ibetween Scaling, and then obtain judgment matrix;
The determination of Scaling is exactly by each data quality accessment index I
icompare between two, determine importance degree, and to importance degree by 1 ~ 9 assignment.
Suppose that two the data quality accessment indexs compared between two are I
kand I
h, wherein I
kand I
hbe respectively I
i(i=1,2 ... n, wherein n is the number of data quality accessment index) in some, the importance Scaling implication table of data quality accessment index is as shown in table 3, suppose Scaling determine after judgment matrix be A=(a
kh)
n × n, a
khrepresent data quality accessment index I
kwith data quality accessment index I
hthe importance result of comparing, judgment matrix A has following character: a
kh>0, a
kh=1/a
hk, a
kk=1.
The importance Scaling implication table of table 3 data quality accessment index
| Implication | Importance degree |
| I kWith I hThere is equal importance | 1 |
| I kCompare I hImportant a little | 3 |
| I kCompare I hObviously important | 5 |
| I kCompare I hStrongly important | 7 |
| I kCompare I hExtremely important | 9 |
| I kCompare I hImportance degree respectively between the intermediate degree of above-mentioned judgement | 2，4，6，8 |
| I hCompare I kImportance degree corresponding with above-mentioned respectively | 1,1/2,1/3…1/9 |
2. all importance degree values in the judgment matrix 1. obtained step carry out row normalized respectively, obtain row normalization matrix;
3. summation operation is carried out to each row of row normalization matrix, obtain row additive value;
4. summation operation is carried out to all row additive values obtained, obtain row and be added total value;
5. calculate the weight of each data quality accessment index, i.e. weight=row additive value/row is added total value.
In embodiments of the invention, correctness I in tentation data quality evaluation index
1than integrality I
2important a little, so a
12=3, the judgment matrix that embodiments of the invention are formed is as shown in table 4:
Table 4 judgment matrix
| Evaluation index | Correctness | Integrality | Uniqueness | Consistance | Accuracy | Validity |
| Correctness | 1 | 3 | 6 | 4 | 4 | 3 |
| Integrality | 1/3 | 1 | 4 | 2 | 2 | 1 |
| Uniqueness | 1/6 | 1/4 | 1 | 1/3 | 1/3 | 1/4 |
| Consistance | 1/4 | 1/2 | 3 | 1 | 1 | 1/2 |
| Accuracy | 1/4 | 1/2 | 3 | 1 | 1 | 1/2 |
| Validity | 1/3 | 1 | 4 | 2 | 2 | 1 |
Data quality accessment index I
irow normalization, row additive value and weight as shown in table 5.Meanwhile, according to the needs of actual assessment object, artificially set the result E desired by each data quality accessment index
i(E
ireal number between 0 to 100%).
The row normalization of table 5 data quality accessment index, row additive value, weight table and expectation value
5) electricity statistical index data D to be assessed is carried out to the detection analysis of each data quality accessment index, and calculate and meet data quality accessment index I
idata number percent S
i(S
ibetween 0 to 100%, i=1,2 ... n, wherein n is the number of data quality accessment index);
Each data quality accessment index I is carried out to electricity statistical index data D to be assessed
idetection analyze time, if electricity statistical index data D to be assessed meets each data quality accessment index I
icorresponding data quality accessment rule R
r(I
i), then illustrate that this electric power statistical indicator number D is all qualified; If there is electricity statistical index data D not meet certain data quality accessment index I
iunder any data quality accessment rule R
r(I
i), then illustrate that this electricity statistical index data D to be assessed does not meet this data quality accessment index I
i, do not meet this data quality accessment index I
ithe number of electricity statistical index data be number of non-compliances.
Each data quality accessment index I is carried out to electricity statistical index data D to be assessed
idetection analyze detailed process be:
(1) correctness detection is carried out to electricity statistical index data D to be assessed;
Because electricity statistical index data may comprise single statistical index data, have multiple statistical index data of direct loic relation and without a certain in multiple statistical indicator numbers of direct loic relation or certain is several, therefore the present invention analyzes these three kinds of data cases respectively, wherein:
1. carry out directly adopting box traction substation to identify underproof data when correctness detects to single electricity statistical index data.
2. whether qualified to there being the electricity statistical index data of direct loic relation to carry out weighing these electricity statistical index data according to the logical relation existed between electricity statistical index data when correctness detects, identify number of non-compliances certificate.
Although there is no direct logical relation between the multiple electricity statistical index data 3. without direct loic relation, but certain correlativity can be had between their major parts, therefore, regretional analysis can be passed through, draw the approximate function between them, by the gap between analyses and prediction value and actual value, identify number of non-compliances certificate.
(2) can pass through to realize the detection of vacancy value when carrying out integrity detection to electricity statistical index data D to be assessed, if there is vacancy value in electricity statistical index data to be assessed, then think that it does not meet integrity metrics, the number of vacancy value is the number not meeting integrity metrics.
(3), when uniqueness detection being carried out to electricity statistical index data D to be assessed, can analyze from following three aspects:
1. judge whether to exist in electric power statistical report form two identical time variables.
2. judge whether to exist in electric power statistical report form two identical statistics entitling.
3. judge whether the whether identical or same number of data that in electric power statistical report form, different row or column is corresponding exceedes a certain threshold values N(N and determine according to the number of electricity statistical index data to be assessed).
If electricity statistical index data D to be assessed meets any one in above-mentioned three, then think that it exists repeating data or has repetition suspicion.For the repeating data that Preliminary detection goes out, carry out analysis and judge, finally determine whether it is "True" and repeat, the data amount check of repetition is the data amount check not meeting uniqueness index.
(4) electricity statistical index data is all numeric type data, the form of arabic numeral is adopted to describe, if all detect its total data when carrying out consistency detection to electricity statistical index data D to be assessed, then can increase unnecessary workload, be reduced to contrast ratio class data when therefore conforming detection being carried out to electricity statistical index data D to be assessed and detect.For ratio class data, have decimal, " % " and "/" three kinds of expression formats, such as, electricity statistical index data line loss per unit can represent with any one in 0.9,90% or 9/10 these three kinds of forms.The conforming detection of electricity statistical index data is carried out according to the following steps:
1. a kind of parameter format is preset;
2. electricity statistical index data D to be assessed and parameter format are analyzed, whether both investigations are consistent, if there are differences, then think that the form of electricity statistical index data D to be assessed is undesirable, undesirable data amount check is the data amount check not meeting coincident indicator.
(5) to electricity statistical index data D to be assessed carry out accuracy detect time, whether the precision mainly investigating electricity statistical index data D to be assessed meets the demands, its Cleaning Principle and coincident indicator similar, its testing process is:
1. the reference precision value of pre-defined electricity statistical index data D to be assessed;
2. calculate the character number after each data radix point ". ", obtain the precision of these data, and for there are not the data of radix point ". ", then direct precision is set to 0;
Whether the precision 3. investigating electricity statistical index data D to be assessed meets predefined reference precision value, and the number not meeting the electricity statistical index data D to be assessed of reference precision value is the data amount check not meeting accuracy index.
(6) when carrying out validation checking to electricity statistical index data D to be assessed, from form validity and the numerical value validity two aspect analysis of electricity statistical index data D to be assessed.Before form efficiency analysis is carried out to electricity statistical index data D to be assessed, first must count all valid formats of each electricity statistical index data D to be assessed, and then all data under this electricity statistical index data D to be assessed and its valid format are contrasted one by one, if the expression format of electricity statistical index data D to be assessed is consistent with valid format, then think that it meets this requirement of form validity, otherwise think that these data do not meet the requirement of form validity.The analysis of numerical value validity judges that the numerical value of each electricity statistical index data to be assessed is whether within a certain codomain scope, such as delivery is positive number, line loss per unit is between 0 to 100%, but for integer class data (such as user's number), except analyzing its numerical values recited, also must meet this requirement of integer.
In embodiments of the invention, according to each data quality accessment index I
icorresponding data quality accessment rule R
r(I
i), the electricity statistical index data D in his-and-hers watches 1 carries out detection analysis and is met each data quality accessment index I
ithe number of electricity statistical index data, i.e. passing number, and calculate and meet each data quality accessment index I
ithe number percent S of electricity statistical index data
i, namely qualified number percent, as shown in table 6.
The expectation value that the qualified percentage of the electricity statistical index data that table 6 is to be assessed when sets
| Evaluation index I i | Weights W i | Passing number | Qualified number percent S i(%) | Expectation value E i% |
| Correctness | 0.4081 | 71 | 98.6 | 98 |
| Integrality | 0.1734 | 71 | 98.6 | 98 |
| Uniqueness | 0.0439 | 72 | 100 | 100 |
| Consistance | 0.1006 | 72 | 100 | 100 |
| Accuracy | 0.1006 | 66 | 91.7 | 98 |
| Validity | 0.1734 | 68 | 94.4 | 98 |
6) according to weights W
i, qualified number percent S
iwith the expectation value E of setting
i, calculate the comprehensive assessment value SA of electricity statistical index data, overall expectation value SE and relative difference SR respectively, and the quality overall to electricity statistical index data D to be assessed according to the opinion rating of setting is assessed;
Comprehensive assessment value SA, overall expectation value SE and relative difference SR are determined by following formula respectively.
In formula, SA reflects the True Data quality condition that electricity statistical index data D to be assessed is overall, the expectation value that SE reflection is overall to electricity statistical index data D to be assessed, SR reflects the quality condition of electricity statistical index data D to be assessed relative to overall expectation value SE, and n is the number of data quality accessment index.
According to comprehensive assessment value SA, to the overall data quality level set opinion rating of electricity statistical index data D to be assessed, quality testing table of grading is as shown in table 7.
Table 7 quality testing table of grading
| Comprehensive assessment value SA | Quality testing grade |
| SA∈(95，100］ | Excellent |
| SA∈(90，95］ | Good |
| SA∈(85，90］ | In |
| SA∈(0，85］ | Difference |
For the relative difference SR of electricity statistical index data D to be assessed, if SR symbol is just, overall expectation value SE is larger for its numeric ratio, then illustrate that the quality of data of electricity statistical index data D to be assessed is better than what expect; If SR symbol is negative, overall expectation value SE is larger for its numeric ratio, then the poorer of the quality of data ratio expection that electricity statistical index data D to be assessed is overall is described.
In embodiments of the invention, the comprehensive assessment value that can calculate electricity statistical index data according to the data of table 6 is 97.37988, and overall expectation value is 98.289, and relative difference is-0.90912, draws the following conclusions:
The comprehensive assessment value of electricity statistical index data 1. to be assessed is 97.37988, is greater than 95, and the quality level of electricity statistical index data therefore to be assessed belongs to " excellent ".
2. relative difference is-0.90912, the difference of the quality level ratio expection that electricity statistical index data D to be assessed is overall is described, but gap is little.
7) process underproof electricity statistical index data, to improve the quality of electricity statistical index data D to be assessed, concrete processing procedure is: revise the electricity statistical index data of exception; The electricity statistical index data of disappearance is filled up; The electricity statistical index data repeated is deleted; Expression format disunity, electricity statistical index data that numerical value is invalid are revised; The underproof electricity statistical index data of logarithm value precision is modified; The electricity statistical index data not strong to existing research availability is deleted.
In above-described embodiment, data quality accessment index of the present invention can also comprise ageing, ageing detection can be carried out to electricity statistical index data to be assessed, because of identical electricity statistical index data different year, the electric power statistics in different month also exists identical rule usually, and also can there is identical rule with the January in multiple electricity statistical index data of different year, therefore, when ageing detection is carried out to electricity statistical index data D to be assessed, by drawing multi-thread line chart, the data in same month can be depicted on same statistical graph, contrast the lifting of each line chart, the Changing Patterns such as spacing, the relation of quality of data statistical indicator and time can be disclosed comparatively intuitively.This shows, ageingly closely to be connected with time parameter, may not having so do not meet ageing electricity statistical index data, also may be the data of a year or several years, occurs that the possibility not meeting ageing electricity statistical index data is just larger like this.Generally, the electricity statistical index data in relevant time can be chosen according to the needs of purpose of appraisals when choosing electricity statistical index data to be assessed, therefore, ageing if not being concerned about very much, just can not choose this data quality accessment index, or give this data quality accessment index less weight.
The various embodiments described above are only for illustration of the present invention, and wherein the implementation step of method all can change to some extent, and every equivalents of carrying out on the basis of technical solution of the present invention and improvement, all should not get rid of outside protection scope of the present invention.
Claims (10)
1. a method for evaluating quality for electricity statistical index data, it comprises the following steps:
1) according to the needs of actual assessment object, electricity statistical index data is arranged, obtain electricity statistical index data to be assessed;
2) according to described electricity statistical index data to be assessed, corresponding data quality accessment index I is selected
i, i=1 ..., n, n are the number of data quality accessment index;
3) according to electricity statistical index data to be assessed and selected data quality accessment index I
i, formulate the data quality accessment rule R that each data quality accessment index is corresponding
r(I
i); Wherein each data quality accessment rule R
r(I
i) according to the characteristic sum attribute of electricity statistical index data to be assessed and selected data quality accessment index I
idefinition formulate;
4) each data quality accessment index I is calculated
iweights W
iand respective settings expectation value E
i, expectation value E
ifor the real number between 0 to 100%;
5) according to step 3) the middle data quality accessment rule R formulated
r(I
i), detection is carried out to electricity statistical index data to be assessed and analyzes, and calculate and meet each data quality accessment index I
iqualified number percent S
i, S
ibetween 0 to 100;
6) according to step 4) weights W that calculates
i, qualified number percent S
iwith the expectation value E of setting
i, calculate the comprehensive assessment value SA of described electricity statistical index data to be assessed, overall expectation value SE and relative difference SR respectively, and according to the opinion rating of setting, described electricity statistical index data oeverall quality to be assessed assessed; Wherein, comprehensive assessment value SA, overall expectation value SE and relative difference SR are determined by following formula respectively:
In formula, SA reflects the True Data quality condition that electricity statistical index data D to be assessed is overall, the expectation value that SE reflection is overall to electricity statistical index data D to be assessed, SR reflects the quality condition of electricity statistical index data D to be assessed relative to overall expectation value SE, and n is the number of data quality accessment index;
7) the defective electricity statistical index data evaluated is processed.
2. the method for evaluating quality of a kind of electricity statistical index data as claimed in claim 1, it is characterized in that: also comprise step 8) relative difference SR and overall expectation value SE is compared, obtain electricity statistical index data D to be assessed totally relative to the quality condition of overall expectation value SE, detailed process is: if SR symbol is just, overall expectation value SE is larger for its numeric ratio, then better than expection of the overall quality of data of described electricity statistical index data to be assessed is described; If SR symbol is negative, overall expectation value SE is larger for its numeric ratio, then the poorer of the quality of data ratio expection that described electricity statistical index data to be assessed is overall is described.
3. the method for evaluating quality of a kind of electricity statistical index data as claimed in claim 1, is characterized in that: described step 2) in data quality accessment index be correctness, integrality, uniqueness, consistance, accuracy, validity and ageing in some or certain is several.
4. the method for evaluating quality of a kind of electricity statistical index data as claimed in claim 2, is characterized in that: described step 2) in data quality accessment index be correctness, integrality, uniqueness, consistance, accuracy, validity and ageing in some or certain is several.
5. the method for evaluating quality of a kind of electricity statistical index data as described in any one of Claims 1 to 4, is characterized in that: described step 4) each quality evaluation index I of middle calculating
iweights W
iadopt analytical hierarchy process, the steps include:
1. according to data quality accessment index I
iimportance Scaling implication table, determine each data quality accessment index I by list mode
ibetween Scaling, and then obtain judgment matrix;
2. all importance degree values in the judgment matrix 1. obtained step carry out row normalized respectively, obtain row normalization matrix;
3. summation operation is carried out to each row of row normalization matrix, obtain row additive value;
4. carrying out summation operation to obtaining all row additive values, obtaining row and being added total value;
5. each data quality accessment index I is calculated
iweight, i.e. weight=row additive value/row is added total value.
6. the method for evaluating quality of a kind of electricity statistical index data as described in any one of Claims 1 to 4, it is characterized in that: described step 6) in opinion rating be: if SA ∈ (95, 100] the overall data quality level of electricity statistical index data to be assessed is then evaluated for " excellent ", if SA ∈ (90, 95] the overall data quality level of electricity statistical index data to be assessed is then evaluated for " good ", if SA ∈ (85, 90] then evaluate the overall data quality level of electricity statistical index data to be assessed for " in ", if SA ∈ (0, 85] the overall data quality level of electricity statistical index data to be assessed is then evaluated for " poor ".
7. the method for evaluating quality of a kind of electricity statistical index data as claimed in claim 5, it is characterized in that: described step 6) in opinion rating be: if SA ∈ (95, 100] the overall data quality level of electricity statistical index data to be assessed is then evaluated for " excellent ", if SA ∈ (90, 95] the overall data quality level of electricity statistical index data to be assessed is then evaluated for " good ", if SA ∈ (85, 90] then evaluate the overall data quality level of electricity statistical index data to be assessed for " in ", if SA ∈ (0, 85] the overall data quality level of electricity statistical index data to be assessed is then evaluated for " poor ".
8. the method for evaluating quality of a kind of electricity statistical index data as described in Claims 1 to 4,7 any one, it is characterized in that: described step 7) in the underproof electricity statistical index data evaluated is processed, its concrete processing procedure comprises: revise the electricity statistical index data of exception; The electricity statistical index data of disappearance is filled up; The electricity statistical index data repeated is deleted; Expression format disunity, electricity statistical index data that numerical value is invalid are revised; The underproof electricity statistical index data of logarithm value precision is modified; The electricity statistical index data not strong to existing research availability is deleted.
9. the method for evaluating quality of a kind of electricity statistical index data as claimed in claim 5, it is characterized in that: described step 7) in the underproof electricity statistical index data evaluated is processed, its concrete processing procedure comprises: revise the electricity statistical index data of exception; The electricity statistical index data of disappearance is filled up; The electricity statistical index data repeated is deleted; Expression format disunity, electricity statistical index data that numerical value is invalid are revised; The underproof electricity statistical index data of logarithm value precision is modified; The electricity statistical index data not strong to existing research availability is deleted.
10. the method for evaluating quality of a kind of electricity statistical index data as claimed in claim 6, it is characterized in that: described step 7) in the underproof electricity statistical index data evaluated is processed, its concrete processing procedure comprises: revise the electricity statistical index data of exception; The electricity statistical index data of disappearance is filled up; The electricity statistical index data repeated is deleted; Expression format disunity, electricity statistical index data that numerical value is invalid are revised; The underproof electricity statistical index data of logarithm value precision is modified; The electricity statistical index data not strong to existing research availability is deleted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310163339.9A CN103247008B (en) | 2013-05-07 | 2013-05-07 | A kind of method for evaluating quality of electricity statistical index data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310163339.9A CN103247008B (en) | 2013-05-07 | 2013-05-07 | A kind of method for evaluating quality of electricity statistical index data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103247008A CN103247008A (en) | 2013-08-14 |
| CN103247008B true CN103247008B (en) | 2015-10-28 |
Family
ID=48926515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310163339.9A Active CN103247008B (en) | 2013-05-07 | 2013-05-07 | A kind of method for evaluating quality of electricity statistical index data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103247008B (en) |
Families Citing this family (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103606009B (en) * | 2013-12-10 | 2016-09-21 | 积成电子股份有限公司 | Power distribution network measuring quality appraisal procedure based on minimum distribution region |
| CN103902451A (en) * | 2014-03-26 | 2014-07-02 | 国家电网公司 | Intelligent electricity meter software quality evaluation method |
| CN103942602B (en) * | 2014-04-11 | 2017-01-18 | 浙江大学 | Comprehensive evaluation method for turbogenerator stator end portion winding fixing structure schemes |
| CN104090560B (en) * | 2014-05-06 | 2017-02-08 | 内蒙古云谷电力科技股份有限公司 | Device monitoring power supply integrated environment evaluation indexes |
| CN104112204A (en) * | 2014-07-01 | 2014-10-22 | 国家电网公司 | Evaluation method for efficient operation of power supply quality |
| CN104574201A (en) * | 2014-11-14 | 2015-04-29 | 陕西省地方电力（集团）有限公司榆林电力分公司 | Electric energy quality data reduction evaluation method suitable for multiple purposes |
| CN105005878B (en) * | 2015-08-12 | 2018-05-25 | 国家电网公司 | A kind of comprehensive estimation method of strong intelligent grid |
| CN105307202B (en) * | 2015-09-24 | 2019-01-29 | 珠海许继芝电网自动化有限公司 | A kind of power distribution automation wireless communication usability evaluation method |
| CN105976120A (en) * | 2016-05-17 | 2016-09-28 | 全球能源互联网研究院 | Electric power operation monitoring data quality assessment system and method |
| CN106649840A (en) * | 2016-12-30 | 2017-05-10 | 国网江西省电力公司经济技术研究院 | Method suitable for power data quality assessment and rule check |
| CN106874483A (en) * | 2017-02-20 | 2017-06-20 | 山东鲁能软件技术有限公司 | A kind of device and method of the patterned quality of data evaluation and test based on big data technology |
| CN107463532A (en) * | 2017-06-28 | 2017-12-12 | 国网上海市电力公司 | A kind of mass analysis method of electric power statistics |
| CN107633257B (en) * | 2017-08-15 | 2020-04-17 | 上海数据交易中心有限公司 | Data quality evaluation method and device, computer readable storage medium and terminal |
| CN107516171B (en) * | 2017-08-31 | 2021-02-02 | 湖北国网华中科技开发有限责任公司 | Prediction analysis system and analysis method for key operation indexes of power grid enterprise |
| CN107908558B (en) * | 2017-11-14 | 2021-01-05 | 广东华仝九方科技有限公司 | Automatic evaluation method for mobile phone client software quality |
| CN108038132A (en) * | 2017-11-17 | 2018-05-15 | 上海数据交易中心有限公司 | Data Quality Analysis method and device, storage medium, terminal |
| CN108197280B (en) * | 2018-01-10 | 2022-05-13 | 上海电气集团股份有限公司 | Mining ability evaluation method based on industrial equipment data |
| CN108829750A (en) * | 2018-05-24 | 2018-11-16 | 国信优易数据有限公司 | A kind of quality of data determines system and method |
| CN108898311A (en) * | 2018-06-28 | 2018-11-27 | 国网湖南省电力有限公司 | A kind of data quality checking method towards intelligent distribution network repairing dispatching platform |
| CN109492683A (en) * | 2018-10-30 | 2019-03-19 | 国网湖南省电力有限公司 | A kind of quick online evaluation method for the wide area measurement electric power big data quality of data |
| CN110069393A (en) * | 2019-03-11 | 2019-07-30 | 北京互金新融科技有限公司 | Detection method, device, storage medium and the processor of software environment |
| CN110033201A (en) * | 2019-04-22 | 2019-07-19 | 浙江中烟工业有限责任公司 | A kind of tobacco industry batch overall process quality testing and improved method and apparatus |
| CN111210123A (en) * | 2019-12-26 | 2020-05-29 | 国网浙江省电力有限公司杭州供电公司 | Quality evaluation method for big data of operation of regulation and control cloud power grid |
| CN113434490B (en) * | 2020-03-23 | 2024-04-12 | 北京京东振世信息技术有限公司 | Quality detection method and device for offline imported data |
| CN111861093A (en) * | 2020-05-27 | 2020-10-30 | 京杭运河江苏省交通运输厅苏北航务管理处 | Ship lock equipment and facility grading evaluation method |
| CN112348695A (en) * | 2020-09-16 | 2021-02-09 | 贵州电网有限责任公司 | Electric power data quality evaluation model construction method based on analytic hierarchy process |
| CN112486961A (en) * | 2020-11-18 | 2021-03-12 | 广西电网有限责任公司电力科学研究院 | Method and device for processing big data in real time |
| CN112380190B (en) * | 2020-11-27 | 2021-08-17 | 北京三维天地科技股份有限公司 | Data quality health degree analysis method and system based on multidimensional analysis technology |
| CN113376469A (en) * | 2021-06-29 | 2021-09-10 | 四川大学 | Analysis method of power quality disturbance data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246569A (en) * | 2008-02-28 | 2008-08-20 | 江苏省电力试验研究院有限公司 | Electric network energy quality synthetic appraisement method based on analytic hierarchy process and fuzzy algorithm |
| CN101465546A (en) * | 2009-01-08 | 2009-06-24 | 上海交通大学 | Electric energy quality synthesis evaluation system |
-
2013
- 2013-05-07 CN CN201310163339.9A patent/CN103247008B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101246569A (en) * | 2008-02-28 | 2008-08-20 | 江苏省电力试验研究院有限公司 | Electric network energy quality synthetic appraisement method based on analytic hierarchy process and fuzzy algorithm |
| CN101465546A (en) * | 2009-01-08 | 2009-06-24 | 上海交通大学 | Electric energy quality synthesis evaluation system |
Non-Patent Citations (3)
| Title |
|---|
| 基于层次分析法的现状电网评估方法研究;李晓辉 等;《电力***保护与控制》;20080716;第36卷(第14期);57-61 * |
| 数据质量研究综述;韩京宇 等;《计算机科学》;20080225;第35卷(第2期);1-5 * |
| 电网企业信息化指标体系及评价方法探讨;陈永权 等;《电力信息化》;20040220;第2卷(第2期);18-20 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103247008A (en) | 2013-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103247008B (en) | A kind of method for evaluating quality of electricity statistical index data | |
| US10120912B2 (en) | System and method for combination-based data analysis | |
| CN107169628B (en) | Power distribution network reliability assessment method based on big data mutual information attribute reduction | |
| CN108898311A (en) | A kind of data quality checking method towards intelligent distribution network repairing dispatching platform | |
| CN102609778B (en) | Method and device for assessing risk of electric power communication network | |
| CN104268678A (en) | Preventative device maintenance method based on dynamic reliability | |
| CN102280874A (en) | Platform-area line loss rate detecting system | |
| CN104573989A (en) | Transmission line fault probability assessment method based on historical fault information | |
| CN103366123A (en) | Software risk assessment method based on defect analysis | |
| CN104376413A (en) | Power grid planning scheme evaluation system based on analytic hierarchy process and data envelopment analysis | |
| CN104299116A (en) | Quantitative evaluation method for security risk of operation of power network | |
| Wang et al. | An AHP-weighted aggregated data quality indicator (AWADQI) approach for estimating embodied energy of building materials | |
| CN106295858A (en) | A kind of electric energy meter non-health degree Forecasting Methodology | |
| CN114065223A (en) | Multi-dimensional software security risk assessment method based on CVSS | |
| CN111582568A (en) | Electric power data-based enterprise rework prediction method during spring festival | |
| CN105354371A (en) | GA-WNN based power transmission and transformation project construction cost prediction method | |
| CN112084678A (en) | Wire loss rate processing method and device based on multiple regression | |
| CN112101761A (en) | Comprehensive evaluation method for construction effect of clean, low-carbon, safe and efficient energy system | |
| CN103914482A (en) | CMDB (Configuration Management Date Base) based centralized monitoring event influence determination method | |
| CN108182511A (en) | It is a kind of based on Demand Side Response reserve value assessment method of the sum of ranks than method | |
| CN110764043B (en) | Equipment quality condition evaluation method suitable for continuous measurement results | |
| Yuan et al. | LMP step pattern detection based on real-time data | |
| Efthimiou et al. | Statistical projection of material intensity: evidence from the global economy and 107 countries | |
| CN112365187A (en) | Generating set market force abuse identification method based on Lasso-logit model | |
| Kasperowicz et al. | Reengineering of electricity market monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |